Wavelet Features Extraction

✉️ Mailing List Archive (read-only)
1

External Email - Use Caution

Greetings,

I use short time Fourier transform to extract features from the time-series
EEG signals. Now I plan to use Wavelet that I don't have any prior
experience in.

Can someone provide a Python implementation (or MNE - btw, I couldn't
digest mne morlet for some reason!)? Also, what output I should expect, and
what features can be computed from the Wavelet transform output to be ready
to fit a learner?

A question I would also like to ask those who're concerned about feature
extraction, why would I use Wavelet over STFT, or vice versa?

Thank you,
Badar Almarri
Graduate Student
Dept. of Computer Science and Engr.
University of Connecticut
badar.almarri at uconn.edu
<http://www.linkedin.com/pub/badar-almarri/48/b09/8b8>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mail.nmr.mgh.harvard.edu/pipermail/mne_analysis/attachments/20180803/4f3d06ab/attachment.html

2

External Email - Use Caution

Hi,

If you're interested in feature extraction, you might want to look into
mne-features: https://mne-tools.github.io/mne-features/api.html.

It should fit your needs.

Best,
Mainak

3

External Email - Use Caution

Hey hi !

If you are interested in a good explanation of what you will find
extracting features between STFT, Wavelets and eventually MP, check out
this excellent paper: http://www.jneurosci.org/content/36/12/3399.short

Your regards!

2018-08-03 20:53 GMT-03:00 Mainak Jas <mainakjas at gmail.com>:

        External Email - Use Caution

Hi,

If you're interested in feature extraction, you might want to look into
mne-features: API Documentation — mne_features 0.2 documentation.

It should fit your needs.

Best,
Mainak

        External Email - Use Caution

Greetings,

I use short time Fourier transform to extract features from the
time-series EEG signals. Now I plan to use Wavelet that I don't have any
prior experience in.

Can someone provide a Python implementation (or MNE - btw, I couldn't
digest mne morlet for some reason!)? Also, what output I should expect, and
what features can be computed from the Wavelet transform output to be ready
to fit a learner?

A question I would also like to ask those who're concerned about feature
extraction, why would I use Wavelet over STFT, or vice versa?

Thank you,
Badar Almarri
Graduate Student
Dept. of Computer Science and Engr.
University of Connecticut
badar.almarri at uconn.edu
<http://www.linkedin.com/pub/badar-almarri/48/b09/8b8&gt;

_______________________________________________
Mne_analysis mailing list
Mne_analysis at nmr.mgh.harvard.edu
Mne_analysis Info Page

The information in this e-mail is intended only for the person to whom it
is
addressed. If you believe this e-mail was sent to you in error and the
e-mail
contains patient information, please contact the Partners Compliance
HelpLine at
MyComplianceReport.com: Compliance and Ethics Reporting . If the e-mail was sent to you
in error
but does not contain patient information, please contact the sender and
properly
dispose of the e-mail.

_______________________________________________
Mne_analysis mailing list
Mne_analysis at nmr.mgh.harvard.edu
Mne_analysis Info Page

The information in this e-mail is intended only for the person to whom it
is
addressed. If you believe this e-mail was sent to you in error and the
e-mail
contains patient information, please contact the Partners Compliance
HelpLine at
MyComplianceReport.com: Compliance and Ethics Reporting . If the e-mail was sent to you in
error
but does not contain patient information, please contact the sender and
properly
dispose of the e-mail.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mail.nmr.mgh.harvard.edu/pipermail/mne_analysis/attachments/20180806/6e6ac219/attachment.html

4

External Email - Use Caution

If you're interested in feature extraction, you might want to look into mne-features: API Documentation — mne_features 0.2 documentation.

This is great! Could this library be advertised somewhere in the
MNE-Python website or documentation? This would avoid people (like me
:slight_smile: reinventing the wheel.

And perhaps more generally, could we have something equivalent to
scikit-learn-contrib
(https://github.com/scikit-learn-contrib/scikit-learn-contrib/blob/master/README.md),
to collect MNE-compatible projects?

Alejandro

5

External Email - Use Caution

Thank you, all!

Best,
Badar Almarri
Graduate Student
Dept. of Computer Science and Engr.
University of Connecticut
badar.almarri at uconn.edu
<http://www.linkedin.com/pub/badar-almarri/48/b09/8b8>

6

External Email - Use Caution

hi,

> If you're interested in feature extraction, you might want to look into mne-features: API Documentation — mne_features 0.2 documentation.

This is great! Could this library be advertised somewhere in the
MNE-Python website or documentation? This would avoid people (like me
:slight_smile: reinventing the wheel.

I did not advertise it too much so far as it's still under construction.

And perhaps more generally, could we have something equivalent to
scikit-learn-contrib
(https://github.com/scikit-learn-contrib/scikit-learn-contrib/blob/master/README.md),
to collect MNE-compatible projects?

yes we could do this. We probably need someone to volunteer to coordinate this.

Alex